User | peterb123 |
Upload Date | November 04 2024 10:24 AM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.0.1 (Build 24A348) |
Model | Mac Studio (2023) |
Model ID | Mac14,14 |
Motherboard | Mac14,14 |
CPU Information | |
---|---|
Name | Apple M2 Ultra |
Topology | 1 Processor, 24 Cores |
Identifier | Apple M2 Ultra |
Base Frequency | 3.48 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1470
273.3 IPS |
|
Image Classification (HP)
|
100% |
13042
2.43 KIPS |
|
Image Classification (Q)
|
96% |
15701
2.93 KIPS |
|
Image Segmentation (SP)
|
100% |
1773
28.7 IPS |
|
Image Segmentation (HP)
|
100% |
10177
165.0 IPS |
|
Image Segmentation (Q)
|
99% |
11376
184.4 IPS |
|
Pose Estimation (SP)
|
100% |
19094
22.3 IPS |
|
Pose Estimation (HP)
|
100% |
105156
122.7 IPS |
|
Pose Estimation (Q)
|
95% |
103718
121.6 IPS |
|
Object Detection (SP)
|
100% |
1861
147.6 IPS |
|
Object Detection (HP)
|
99% |
15915
1.27 KIPS |
|
Object Detection (Q)
|
91% |
17561
1.40 KIPS |
|
Face Detection (SP)
|
100% |
3676
43.7 IPS |
|
Face Detection (HP)
|
100% |
35315
419.6 IPS |
|
Face Detection (Q)
|
100% |
45363
539.0 IPS |
|
Depth Estimation (SP)
|
100% |
6464
49.8 IPS |
|
Depth Estimation (HP)
|
99% |
85588
659.4 IPS |
|
Depth Estimation (Q)
|
85% |
106809
834.7 IPS |
|
Style Transfer (SP)
|
100% |
27163
34.9 IPS |
|
Style Transfer (HP)
|
100% |
205158
263.7 IPS |
|
Style Transfer (Q)
|
96% |
190115
245.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5990
221.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
39409
1.46 KIPS |
|
Image Super-Resolution (Q)
|
99% |
47342
1.75 KIPS |
|
Text Classification (SP)
|
100% |
2343
3.13 KIPS |
|
Text Classification (HP)
|
100% |
4025
5.37 KIPS |
|
Text Classification (Q)
|
93% |
3991
5.36 KIPS |
|
Machine Translation (SP)
|
100% |
5033
86.7 IPS |
|
Machine Translation (HP)
|
100% |
2049
35.3 IPS |
|
Machine Translation (Q)
|
98% |
2040
35.3 IPS |